Chatbots Are Changing Our World as We Know It
By Justin Snyder – Technical Lead, Digital Workplace @ Plus Consulting
Here is the logic flow of a Commerce bot that functions as a concierge for a hotel:
1. The customer uses the hotel mobile app.
2. Using Azure AD B2C, the user authenticates.
3. Using the custom Application Bot, the user requests information.
4. Cognitive Services helps process the natural language request.
5. The response is reviewed by a customer who can refine the question using natural conversation.
6. After the user is happy with the results, the Application Bot updates the customer’s reservation.
7. Application insights gather runtime telemetry to help development with bot performance and usage.
Informational and Q&A Support
An informational bot can answer questions defined in a knowledge set or FAQ using Cognitive Services QnA Maker and answer more open-ended questions by using Azure Search.
Often information is buried in structured data stores like SQL Server that can be easily surfaced via search. Imagine looking up a customer's order status by simple conversational commands. Using Cognitive Services QnA Maker, the user is presented with a set of valid search options like lookup a customer, review a customer's most recent order, etc. With the QnA format defined the user can easily ask questions that are backed by Azure Search which can look up data stored in a SQL Database. Below is an example from Microsoft on how an Informational Bot could work.
Here is the logic flow of an Information bot:
1. The employee starts the Information bot.
2. Azure Active Directory validates the employee's identity.
3. The employee can ask the bot what type of queries are supported.
4. Cognitive Services returns an FAQ bot built with the QnA Maker.
5. The employee defines a valid query.
6. The bot submits the query to Azure Search which returns information about the application data.
7. Application insights gather runtime telemetry to help development with bot performance and usage.
Productivity
An enterprise productivity bot can increase your productivity by integrating a bot with your Office 365 calendar and other services.
Quickly accessing customer information without having to have a bunch of windows open is what the Enterprise Productivity Bot is all about. Using simple chat commands, a sales rep can look up a customer and check their next appointment via the Graph API and Office 365. From there they can access customer-specific information stored in CRM such as get a case or create a new one. Below is an example from Microsoft showing how a productivity bot could be set up.
Here is the logic flow of an Enterprise Productivity bot:
1. The employee accesses the Enterprise Productivity bot.
2. Azure Active Directory validates the employee's identity.
3. The Enterprise Productivity bot can query the employee's Office 365 calendar via the Azure Graph.
4. Using data gathered from the calendar, the bot accesses case information in Dynamics CRM.
5. The information is returned to the employee who can filter down the data without leaving the bot.
6. Application insights gather runtime telemetry to help development with bot performance and usage.
Artificial Intelligence (AI) and Machine Learning (ML) are rapidly becoming the focus for innovation in our tech industry. Tech giants like Microsoft, Amazon, and IBM are doubling down on their investments to push their teams working on their AI and ML initiatives as high as they can go. Chatbots are one of the major outputs of this investment and one of the best use cases for any industry. Artificial Intelligence is here, we just have to work with it.
What exactly are chatbots?
A chatbot or conversational bot is a program, typically a web service, that attempts to imitate the conversation of a human being via text or speech interactions. A user can send a chatbot a request or a question, and the chatbot responds and or executes the action. Chatbots are the middle-man for AI. This form of interfacing with AI is widely leveraged in businesses across sales and service departments and the consumer app and device market.How do chatbots work?
To illustrate how chatbots work we will look at Microsoft’s platform for AI and ML in Azure. An Azure Bot Service instance in Azure provides a scalable, integrated bot development and hosting environment for conversational bots that can reach users across multiple channels on any device. Bots provide the conversational interface that accepts user input in different mediums including text, speech, cards, or images. The Azure Bot Service offers a set of fourteen channels to interact with users including Cortana, Facebook Messenger, Skype, etc. Intelligence is enabled in the Azure Bot Service through the cloud AI services forming the bot brain that understands and reasons about the user input. Based on understanding the input, the bot can help the user complete some tasks, answer questions, or even chit chat through action handlers. The following diagram summarizes how Azure Bot Services enable conversational AI applications and the Cloud AI services including language understanding, speech recognition, Q&A Maker, etc. Language Understanding (LUIS) is the key part of the bot brain that allows the bot to understand natural language input and reason about it to take the appropriate action. As customization is critical for every business scenario, Language Understanding helps build custom models for your business vertical with little effort and without prior expertise in data science. Designed to identify valuable information in conversations, it interprets user goals (intents) and distills valuable information from sentences (entities), for a high quality, nuanced language model.How chatbots are disrupting business
Commerce A commerce bot can replace the traditional e-mail and phone call interactions that people typically have with a hotel's concierge service. The bot takes advantage of Cognitive Services to better process customer requests via text and voice with context gathered from integration with backend services. Below is an example from Microsoft on how a commerce bot could work.
Here is the logic flow of a Commerce bot that functions as a concierge for a hotel:
1. The customer uses the hotel mobile app.
2. Using Azure AD B2C, the user authenticates.
3. Using the custom Application Bot, the user requests information.
4. Cognitive Services helps process the natural language request.
5. The response is reviewed by a customer who can refine the question using natural conversation.
6. After the user is happy with the results, the Application Bot updates the customer’s reservation.
7. Application insights gather runtime telemetry to help development with bot performance and usage.
Informational and Q&A Support
An informational bot can answer questions defined in a knowledge set or FAQ using Cognitive Services QnA Maker and answer more open-ended questions by using Azure Search.
Often information is buried in structured data stores like SQL Server that can be easily surfaced via search. Imagine looking up a customer's order status by simple conversational commands. Using Cognitive Services QnA Maker, the user is presented with a set of valid search options like lookup a customer, review a customer's most recent order, etc. With the QnA format defined the user can easily ask questions that are backed by Azure Search which can look up data stored in a SQL Database. Below is an example from Microsoft on how an Informational Bot could work.
Here is the logic flow of an Information bot:
1. The employee starts the Information bot.
2. Azure Active Directory validates the employee's identity.
3. The employee can ask the bot what type of queries are supported.
4. Cognitive Services returns an FAQ bot built with the QnA Maker.
5. The employee defines a valid query.
6. The bot submits the query to Azure Search which returns information about the application data.
7. Application insights gather runtime telemetry to help development with bot performance and usage.
Productivity
An enterprise productivity bot can increase your productivity by integrating a bot with your Office 365 calendar and other services.
Quickly accessing customer information without having to have a bunch of windows open is what the Enterprise Productivity Bot is all about. Using simple chat commands, a sales rep can look up a customer and check their next appointment via the Graph API and Office 365. From there they can access customer-specific information stored in CRM such as get a case or create a new one. Below is an example from Microsoft showing how a productivity bot could be set up.
Here is the logic flow of an Enterprise Productivity bot:
1. The employee accesses the Enterprise Productivity bot.
2. Azure Active Directory validates the employee's identity.
3. The Enterprise Productivity bot can query the employee's Office 365 calendar via the Azure Graph.
4. Using data gathered from the calendar, the bot accesses case information in Dynamics CRM.
5. The information is returned to the employee who can filter down the data without leaving the bot.
6. Application insights gather runtime telemetry to help development with bot performance and usage.
Artificial Intelligence (AI) and Machine Learning (ML) are rapidly becoming the focus for innovation in our tech industry. Tech giants like Microsoft, Amazon, and IBM are doubling down on their investments to push their teams working on their AI and ML initiatives as high as they can go. Chatbots are one of the major outputs of this investment and one of the best use cases for any industry. Artificial Intelligence is here, we just have to work with it.